Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5.3-Codex

openai.com

Post reply on HN
Print view View original

301–310 of 634 posts

Re: GPT-5.3-Codex

#301

Post by HAL3000 »

beernet wrote: post #181
nananana9 wrote: post #173

I've been listening to the insane 100x productivity gains you all are getting with AI and "this new crazy model is a real game changer" for a few years now, I think it's about time I asked: Can you guys point me ton a single useful, majority LLM-written, preferably reliable, program that solves a non-trivial problem that hasn't been solved before a bunch of times in publicly available code?

Can you point me to a human written program an LLM cannot write? And no, just answering with a massively large codebase does not count because this issue is temporary. Some people just hate progress.

> Can you point me to a human written program an LLM cannot write?

Sure:

"The resulting compiler has nearly reached the limits of Opus’s abilities. I tried (hard!) to fix several of the above limitations but wasn’t fully successful. New features and bugfixes frequently broke existing functionality.

As one particularly challenging example, Opus was unable to implement a 16-bit x86 code generator needed to boot into 16-bit real mode. While the compiler can output correct 16-bit x86 via the 66/67 opcode prefixes, the resulting compiled output is over 60kb, far exceeding the 32k code limit enforced by Linux. Instead, Claude simply cheats here and calls out to GCC for this phase (This is only the case for x86. For ARM or RISC-V, Claude’s compiler can compile completely by itself.)"[1]

1. https://www.anthropic.com/engineering/building-c-compiler

Re: GPT-5.3-Codex

#302

Post by sealeck »

_zoltan_ wrote: post #297
ghosty141 wrote: post #228

Earlier quoted context omitted.

I'm personally 100% convinced (assuming prices stay reasonable) that the Codex approach is here to stay. Having a human in the loop eliminates all the problems that LLMs have and continously reviewing small'ish chunks of code works really well from my experience. It saves so much time having Codex do all the plumbing so you can focus on the actual "core" part of a feature. LLMs still (and I doubt that changes) can't…

I'm personally 100% convinced of the opposite, that it's a waste of time to steer them. we know now that agentic loops can converge given the proper framing and self-reflectiveness tools.

Converge towards what though... I think the level of testing/verification you need to have an LLM output a non-trivial feature (e.g. Paxos/anything with concurrency, business logic that isn't just "fetch value from spreadsheet, add to another number and save to the database") is pretty high.

Re: GPT-5.3-Codex

#303

Post by readyforbrunch »

StephenHerlihyy wrote: post #167
NitpickLawyer wrote: post #34

Earlier quoted context omitted.

Just some anecdata++ here but I found 5.2 to be really good at code review. So I can have something crunched by cheaper models, reviewed async by codex and then re-prompt with the findings from the review. It finds good things, doesn't flag nits (if prompted not to) and the overall flow is worth it for me. Speed loss doesn't impact this flow that much.

I don’t use OpenAI too much, but I follow a similar work flow. Use Opus for design/architecture work. Move it to Sonnet for implementation and build out. Then finally over to Gemini for review, QC and standards check. There is an absolute gain in using different models. Each has their own style and way of solving the problem just like a human team. It’s kind of awesome and crazy and a bit scary all at once.

How do you orchestrate this workflow? Do you define different skills that all use different models, or something else?

Re: GPT-5.3-Codex

#304

Post by textlapse »

I would love to see a nutritional facts label on how many prompts / % of code / ratio of human involvement needed to use the models to develop their latest models for the various parts of their systems.

Re: GPT-5.3-Codex

#305

Post by satvikpendem »

falloutx wrote: post #257
satvikpendem wrote: post #246

Earlier quoted context omitted.

Why do you believe an LLM can't write these, just because they're 3D? If the assets are given (just as with a human game programmer, who has artists provide them the assets), then an LLM can write the code just the same.

What? People can easily get assets, thats not a even a problem in 2026. Roller coaster tycoon's assets were done by the programmer himself. If its so easy why haven't we seen actually complex pieces of software done in couple of weeks by LLM users? Also try building any complex effects by prompting LLMs, you wont get any far, this is why all of the LLM coded websites look stupidly bland.

Not sure what you're confused about, I never said assets were hard to get, I just said that the LLM needs to be provided a folder of the assets for it to make use of them, it's not going to create them from scratch (at least not without great difficulty, because LLMs are capable of using and coding Three.js for example). I don't know the answer to your first question because I don't hang around in the 3D or game dev fields, I'm sure there are examples of vibe coded games however.

As to your second question, it is about prompting them correctly, for example [0]. Now I don't know about you but some of those sites especially after using the frontend skill look pretty good to me. If those look bland to you then I'm not really sure what you're expecting, keeping in mind that the example you showed with the graphics are not regular sites but more design oriented, and even still nothing stops LLMs from producing such sites.

[0] https://youtu.be/f2FnYRP5kC4

Re: GPT-5.3-Codex

#306

Post by rozumbrada »

Rperry2174 wrote: post #188

Whats interesting to me is that these gpt-5.3 and opus-4.6 are diverging philosophically and really in the same way that actual engineers and orgs have diverged philosophically With Codex (5.3), the framing is an interactive collaborator: you steer it mid-execution, stay in the loop, course-correct as it works. With Opus 4.6, the emphasis is the opposite: a more autonomous, agentic, thoughtful system that plans deepl…

I read this exact comment with I would say completely the same words several times in X and I would bet my money it's LLM generated by someone who has not even tried both the tools. This AI slop even in the site like this without direct monetisation implications from fake engagement is making me sick...

Re: GPT-5.3-Codex

#308

Post by iujasdkjfasf »

vovavili wrote: post #190
cedws wrote: post #93

Earlier quoted context omitted.

I wish they’d just stop pretending to care about safety, other than a few researchers at the top they care about safety only as long as they aren’t losing ground to the competition. Game theory guarantees the AI labs will do what it takes to ensure survival. Only regulation can enforce the limits, self policing won’t work when money is involved.

The last thing I would want is for excessively neurotic bureaucrats to interfere with all the mind-blowing progress we've had in the last couple of years with LLM technology.

[dead]

Re: GPT-5.3-Codex

#309

Post by llmslave »

nananana9 wrote: post #173

I've been listening to the insane 100x productivity gains you all are getting with AI and "this new crazy model is a real game changer" for a few years now, I think it's about time I asked: Can you guys point me ton a single useful, majority LLM-written, preferably reliable, program that solves a non-trivial problem that hasn't been solved before a bunch of times in publicly available code?

baffled that people are still suspicious of ai coding models

Re: GPT-5.3-Codex

#310

Post by timpera »

SunshineTheCat wrote: post #255

I've always been fascinated to see significantly more people talking about using Claude than I see people talking about Codex. I know that's anecdotal, but it just seems Claude is often the default. I'm sure there are key differences in how they handle coding tasks and maybe Claude is even a little better in some areas. However, the note I see the most from Claude users is running out of usage. Coding differences asi…

In my experience, OpenAI gives you unreasonable amounts of compute for €20/month. I am subscribed to both and Claude's limits are so tiny compared to ChatGPT's that it often feels like a rip-off.

Claude also doesn't let you use a worse model after you reach your usage limits, which is a bit hard to swallow when you're paying for the service.

Post reply on HN